National Institute of Technology, Tiruchirappalli 620015 ... 2 of 42 • Head of the Department,...

of 42

DR. M. PUNNIYAMOORTHY

Professor

National Institute of Technology,

Tiruchirappalli – 620015, Tamil Nadu, India.

Career Brief

After completing my M. Tech (IIT, Kharagpur) in Industrial Engineering and Operations Research, I

joined Department of Management Studies, NIT Tiruchirappalli (then REC), in 1987 as a Research

Associate. I am currently Professor, Department of Management Studies-NITT. I completed my Ph.D.

from the Bharathidasan University, Tiruchirappalli. My academic and professional pursuits have over

these years cut across several disciplines. My academic areas of interest include Machine Learning,

Game Theory, Applied Statistics & Data Analysis, Operations Management, Project Management and

Costing, Logistics and Supply Chain Management, and Operations Research & Decision Sciences. I have

also taught courses in these areas as visiting professor to several leading management institutes in India

including the Department of Management Studies IIT-M. I have conducted executive training

programmes. I have authored over 87 papers/articles that have been published / presented at national

and international journals and conferences. I have published a patent (Application No: 201741002082)

on the title of “A Logic to decipher the dynamic architecture from music and vice-versa”. Awarded

Best Paper Award for the paper titled “Strategic Decision Model for Technology Selection” by the

ASME (American Society of Mechanical Engineers) during May 2003. I have authored a book on

production management for Anna University Distance Learning programme, a book on “Service

Quality in Indian Hospitals – perspectives from an emerging market” by Springer Publications

(ISBN 978-3-319-67888-7), a book on “Resource Allocation Problems in Supply Chains” by Emerald

Group Publishing Limited in 2015 (ISBN 178560399X, 9781785603990) and A book on Data Analytics

is getting ready for publication by Pearson Publications. I have also been on the editorial board of

several journals and have been a reviewer for many others.

Work Experience

Primary

Appointment

• Professor, NIT-Tiruchirappalli (Since April 2007)

• Assistant Professor, NIT-Tiruchirappalli (1995-2007)

• Lecturer, NIT-Tiruchirappalli (1988-1995)

• Sr. Research Associate, NIT-Tiruchirappalli (1988-1988)

• Research Associate, NIT-Tiruchirappalli (1987-1988)

Department /

Institution

positions

• Nodal Officer, NIT-Tiruchirappalli (Since 2015)

• Dean – Institute Development, NIT-Tiruchirappalli (2012 to 2015)

of 42

• Head of the Department, ManagementStudies, NIT-Tiruchirappalli

o Period from 28-11-2007 to10-02-2011

o Period from04-02-2004 to21-12-2005

o Period from1991 to 1993

Teaching

Experience

• Taught on an average of 5 Courses every year for the last 5 years

• Consistently rated as the best faculty by the MBA class several times.

Research

Experience

• Published 10 SCI papers

• Published 37 Scopus Indexed Journals

• Have over 18 publications in peer-reviewed Journals

• Threepapers in National Academic / Professional Journals

• Fivepapers in Conference proceedings

• Guided 9 Ph.D., 18 Ph.D. researchesare ongoing, and over 300 MBA Research

Thesis.

Extended

Professional

Activities

• Acted as Director In-chargeintermittentlyat NIT Trichyfor 144 days during the

periods of 2013- 2015.

• I have coordinated five development programs

• I have been a member on various boards, committees,and editorship in journals

Tasks/Responsibilities undertaken as Nodal Officer (SC, ST, OBC, PwDand Minorities) at NIT- T

Activities as a Nodal Officer

• Various welfare schemes are implemented for SC/ST/PwD students and staff members of NIT Trichy

SCSP and TSP plan based on the communication from MHRD.

• The tuition fee is waived for SC/ST students under SCSP and TSP plan.

• Soft skill training to both UG and PG students belongs to SC/ST and PwD.

Periodical interaction with SC/ST students are organized for solving any issue related to academic

and social.

Tasks/Responsibilities undertaken as Dean Institute Development at NIT- T

Activities Carried out as Dean – ID

In charge of Hospital, Guest House, School, Transportation, SC/ST/OBC/Women Cell and PwD

• Hospital

o Specialized Doctors were appointed for Cardio, Diabetes, Homeopathy, Dentist, Radiologist,

Physiotherapist and Ayurvedic

o Dental Chair for filling and scaling.

o Hospital working hours extended to 24X7 with Life Saving Ambulance.

of 42

o Augmented Facilities – Auto counter, Minor OT, Fumigator & Wax bath, 55 Air Conditioned

rooms.

• Guest House

o 55 rooms were Air Conditioned.

o Amenities arranged well equipped with two single cots, cushioned chairs, study table, shoe

racks, coat stand, kettles, LED TV and attached restrooms.

o On-site Facilities: Doctor-on-call, round-the-clock room service, Wi-Fi service, laundry, 24

hours hot & cold water supply, power back-up and travel desk, 2 state of art rooms - hosted

our Honourable President and our Governor, 2 common rooms and a conference hall-

gathering/meeting.

• School

o NIT, Nursery School has been renovated.

o Fencing has been made on all the sides of NIT, Nursery School for safety of the Kids.

o Salary (50%) hike has been made with the patron of Director for all the staff of school.

o New UPS has been procured to solve the problems of Electricity.

• Transport

o Shuttle bus service was arranged within the campus for every one hour, from Admin block

covering all Hostels.

o During Festival holidays and long holidays, the bus trip arranged morning and evening from

junction to NITT and from NITT to junction.

o School services are provided for wards of Staff on payment.

o Buses to pick up and drop all our staff members, both in the morning and evening has

become operational.

• SC/ST/OBC/Women Cell

o Research projects are sanctioned to faculty members belong to SC/ST and PwD under

Scheduled Caste Sub Plan (SCSP), Tribal Sub Plan (TSP) and Persons with Disabilities

(PwD)

o Intern with scholarship is provided to the SC/ST/PwD student under the SCSP, TSP and

PwD plan

o Special lectures are arranged for week SC/ST/PwD students under SCSP and TSP plan

o Specific attention is given to SC/ST/PwD students on various difficult subjects under SCSP

and TSP plan

o Training program on preparation of GATE and CAT for SC/ST students under SCSP and

TSP plan

o Training programme on Communication skill development for employees and wards

o Transport facility has been arranged for those who are residing outside the campus.

o Organized Health Awareness Camp, physiotherapy and Yoga programme periodically

o Health and Fitness practice session arranged for Women employees every week

of 42

o Internal Complaint committee is formed to handle the women harassment issues.

o Women Harassment Cell is functioning to sort-out the harassment related issues

• PwD Cell

o Temporary conveyance facilities (auto rickshaw) have been arranged for PH/PwD Students

within the campus from Hostel to Lecture Hall complex, Library and Hospital and the

expenditure is borne by the institute.

o Any welfare measures related to PH/PwD students will be taken care.

o Temporary residential Quarters have been provided for a period of 3 to 6 months to stay

along with their parents on medical grounds.

Tasks/Responsibilities undertaken as Head of Department at Management Studies, NIT-T

Activities Carried out as HoD

• Instrumental in bringing GD & PI as part of MBA student selection process during 1992-93.

• Conducted & coordinated REC All India MBA Entrance Examination, GD & PI

• Instrumental in bringing in the trimester pattern for MBA during 1992-1993.

• Instrumental in bringing Business Analysis as a specialization in MBA during 2007-11.

• Under my stewardship, Department of Management Studies has been selected as an “Outstanding B-

School (South)” for the National B School Award from Star News for the year 2010.

Tasks/Responsibilities undertaken as Teaching Faculty at Department of Management Studies,

NIT-T

Curriculum Development

• New subjects introduced: Game Theory, Machine Learning, Data Analysis, Supply Chain

Management, Logistics Management, Enterprise Resource Planning, Production Planning and

Control.

• Syllabus revisions were done for all the subjects in the Operations Management area.

Innovative Teaching Method

• Introduced ‘Marathon Task Analysis’ as a part of evaluation for my core subjects.

• Hands on learning for Machine Learning Techniques and Data Analysis, where the students model the

data analysis problem on computers and use large datasets to learn about 15 core data analysis tools

covering Multiple Regression, Conjoint Analysis, Principal Component Analysis, Canonical

Correlation, Multidimensional Scaling, Cluster Analysis, Discriminant Analysis, Factor Analysis,

Support Vector Machines among many others

Other Notable Academic contribution

• A patent entitled “A logic to decipher the dynamic architecture from music and vice-versa” was

of 42

published on Intellectual property of India, July-2018, (Application no: 201741002082).

• The paper titled “Strategic Decision Model for Technology Selection” was selected as one the best

paper for Technology selection by the ASME (American Society of Mechanical Engineers) during

May 2003.

• The book on “Data Analysis for Business Decision” is almost to be completed. This book is shortly in

the process of publication by Pearson Education, India.

• The Solution Manual has been prepared for the reputed book on “PROJECT: Planning, Analysis,

Selection, Financing, Implementation and Review” Written by renowned author Dr.Prasanna Chandra

and it is available online.

• A detailed suggestion has been given to modify the chapter on Credit management in the famous

management text book “Financial Management – Theory and Practice” written by well-known

author Dr. Prasanna Chandra.

• Received an appreciation letter and consultancy was sought by Mr. J.K. Ghose, Additional Chief

Engineer, M.N. Dastur& Co Ltd after studying my article titled – “Economic Justification of FMS”

(IIIE Journal volume XXVII number 6 of June 1998)

• An appreciation letter of appreciation was given by the publisher Palgrave Macmillan for the article,

“An empirical model for brand loyalty measurement”, published in Journal of targeting, measurement

and analysis for marketing.

Task/Responsibilities undertaken as Researcher

Papers in International Academic/ Professional Journals

SCI Journals:

1. Vijaya Prabhagar, M., Punniyamoorthy, M, (2019) “Development of New Agglomerative

and performance evaluation models for classification”, Neural Computing and

applications, published online- 27 June 2019.

2. Sundar R, Punniyamoorthy M, (2019) “Performance enhanced Boosted SVM for Imbalanced

data sets”, Applied Soft Computing, Volume 83, October 2019, 105601

3. Manochandar, S., Punniyamoorthy, M, (2018) “Scaling Feature selection method for

enhancing the classification performance of support vector machines in text mining”,

Computers & Industrial Engineering, Volume 124, October 2018, Pages 139-156

4. Punniyamoorthy, M., & Sridevi, P. (2017). “Influence of fuzzy index parameter on new

membership function for an efficient FCM based FSVM classifier”. Journal of the National

Science Foundation of Sri Lanka, 45(4), pp – 367-379.

5. Punniyamoorthy, M., Mathiyalagan, P., &Parthiban, P. (2011). “A strategic model using

of 42

structural equation modeling and fuzzy logic in supplier selection”.Expert Systems with

Applications, 38(1), Pp- 458-474.

6. Parameshwaran, R., Srinivasan, P. S. S., Punniyamoorthy, M., &Charunyanath, S. T. (2009).

“Integrating fuzzy analytical hierarchy process and data envelopment analysis for performance

management in automobile repair shops.”European Journal of Industrial Engineering, 3(4),

Pp- 450-467.

7. Punniyamoorthy, M., &Ragavan, P. V. (2005). “Justification of automatic storage and retrieval

system (AS/RS) in a heavy engineering industry”. The International Journal of Advanced

Manufacturing Technology, 26(5-6), Pp- 653-658.

8. Ganesh, K., &Punniyamoorthy, M. (2004). “Optimization of continuous-time production

planning using hybrid genetic algorithms-simulated annealing.”The International Journal of

Advanced Manufacturing Technology, 26(1-2), Pp- 148-154.

9. Ragavan, P., &Punniyamoorthy, M. (2003). “A strategic decision model for the justification of

technology selection.”The International Journal of Advanced Manufacturing Technology,

21(1), Pp- 72-78.

10. Aravindan, P., &Punniyamoorthy, M. (2002). “Justification of advanced manufacturing

technologies (AMT).”The International Journal of Advanced Manufacturing Technology,

19(2), 151-156.

11. Sivaguru, M. & Punniyamoorthy, M. (2017), “Modified dynamic fuzzy c-means clustering

algorithm – Application in devising marketing strategies through dynamic retail customer

segmentation”, Applied Intelligence- Under Revision.

12. Sivaguru, M. & Punniyamoorthy, M. (2018), “A modified rough k-means clustering

algorithm”, Pattern recognition - Communicated.

13. Vijaya Prabhagar, M., Punniyamoorthy, M, (2017) “A new initialization and

performance measure for the rough k-means clustering”,Soft Computing.

Communicated.

14. Anu Sendhil, Muthukkumaran, K, Punniyamoorthy, M, Veerapandian, S. A., &Sangeetha,

G, (2017), “Deciphering the frozen music in building Architecture and Vice -Versa process”,

Multimedia tools and applications – Communicated.

15. Sarin Abraham, Punniyamoorthy, M. and Jose Joy Thoppan (2018) “Selection of Nash

Equilibrium in Two-Person Non-Zero Sum Game - A Multi-Criteria Approach”. European

Journal of Industrial Engineering– Communicated.

16. Sarin Abraham, Punniyamoorthy, M. (2018) “Analysis and assessment of divergence of

of 42

final offers in negotiation with reference to Gamma and Beta distribution”. Annals of

Operations Research - Communicated.

17. AnuSendhil, Muthukkumaran, K, Punniyamoorthy, M, Veerapandian, S. A., &Sangeetha, G,

(2018), “Transformations of Architectural and Musical Forms Involved in Visual and Musical

Grid”, Multimedia tools and applications– Communicated.

18. Vijaya Prabhagar, M., Punniyamoorthy, M, (2018) “Means to enhance the performance of

Kohonen Self–Organizing map”, Neurocomputing- Communicated.

19. Manochandar, S., and Punniyamoorthy, M, (2018) “Performance enhancement of a new user

similarity model in collaborative filtering”, Knowledge based system- Communicated.

20. Manochandar, S., Punniyamoorthy, M, Jeyachitra. R.K (2018) “Development of new seed with

performance measurement for K-means clustering”, Computers and Industrial Engineering

(Under Revision).

21. Sarin Abraham, Punniyamoorthy, M. (2019), “A development in the existing non-linear

model and to study its impact on the Nash equilibrium in a two-person non-zero sum game”,

Sadhana – Academy Proceedings in Engineering Sciences(Communicated).

Scopus Indexed Journals:

22. Chitradevi. N, Punniyamoorthy.M (2019), “ Herding behaviour in beta based portfolios”,

International Journal of Management Practices. (Accepted)

23. Maruthamuthu A, Punniyamoorthy M, SwethaManasaPaluru, SindhuraTammuluri (2018)

“Prediction of carotid atherosclerosis in patients with impaired glucose tolerance – A

performance analysis of machine learning techniques” International Journal of Enterprise

Network Management. (In Print)

24. GanapathyG, Sivakumaran N, Punniyamoorthy M, Surendran R, SrijanThokala (2018)

“Comparative study of machine learning techniques for breast cancer identification/diagnosis”

International Journal of Enterprise Network Management,(In Print)

25. Ganapathy G, Sivakumaran N, Punniyamoorthy M, Tryambak chatterjee, Monisha Ravi (2018)

“Improving the prediction accuracy of low back pain using machine learning through data pre-

processing techniques” International Journal of Medical engineering and informatics. (In

print)

26. Punniyamoorthy, M., & Sridevi, P. (2017). “Evaluation of a FCM-based FSVM classifier using

fuzzy index”. International Journal of Enterprise Network Management, 8(1), Pp- 14-34.

27. AntonetteAsumptha, Punniyamoorthy.M, (2017), “A Study on Knowledge Sharing Practices

of 42

among Academicians in India”, Knowledge Management & E-Learning: An International

Journal. (In Print)

28. Ande Raja Ambedkar, Punniyamoorthy.M, Thamaraiselvan.N, (2017), “Modeling Brand

Resonance Score (BRS) –An Application in Financial Services”. Journal of Modelling in

Management (In Print)

29. Ande Raja Ambedkar, Punniyamoorthy.M, Thamaraiselvan.N, (2017), “Brand Resonance Score

for CBBE Model-An Application in Financial Services.”Benchmarking: An International

Journal, Vol. 24 Issue: 6, pp.1490-1507

30. AntonetteAsumptha J, & Punniyamoorthy, M, (2017) “Succession Planning and Knowledge

Management in family owned business firms. International Journal of Pure & Applied

Mathematics. -In Print

31. Punniyamoorthy, M., & Sridevi, P. (2016) “Identification of a standard AI based technique for

credit risk analysis”. Benchmarking: An International Journal, 23(5), Pp- 1381-1390.

32. Sivakumar, P., Ganesh, Punniyamoorthy, M., Lenny Koh, S.C., (2013), “Genetic Algorithm for

Inventory Levels and Routing Structure Optimization in Two Stage Supply Chain”,

International Journal of Information Systems and Supply Chain Management, 6(2), Pp- 33-

49, April-June

33. M.Punniyamoorthy, Rani Susmitha and K.Ganesh (2013), “A study on the impact of

demographics, clinical quality variables and service quality factors on cardiac patient satisfaction

in India”,International Journal of Operational Research.

34. Punniyamoorthy, M., Thamaraiselvan, N., Manikandan, L. (2013). “Assessment of supply chain

risk: Scale development and validation”, Benchmarking: an international Journal, Vol.20,

No.1, Pp- 79-105.

35. Punniyamoorthy, M.,Thoppan, J.J.(2013) “Market manipulation and surveillance – a survey of

literature and some practical implications,”International Journal of Value Chain Management,

Vol. 7, No. 1

36. Punniyamoorthy, M.,Thoppan, J.J.(2013) “ANN-GA based model for Stock Market

Surveillance”,Journal of Financial Crime, Emerald Publications , Vol. 20 No. 1, pp. 52-66.

37. Malairajan, R.A., Ganesh, K., Punniyamoorthy, M. and Anbuudayasankar, S.P. (2013) "Decision

Support System for Real Time Vehicle Routing in Indian Dairy Industry-A Case Study",

International Journal of Information System and Supply Chain management, Vol. 6, No. 3

6(4), 77-101.

38. Kiruthika, A., Chandramohan, S., Punniyamoorthy, M., &Latha, S. (2012). “Evaluation of

service quality of banks–a fuzzy approach”. International Journal of Enterprise Network

http://www.inderscienceonline.com/loi/ijvcm

of 42

Management, 5(4), Pp- 333-354.

39. Punniyamoorty, M., Mathiyalagan, P., & Lakshmi, G. (2012) “A combined application of

structural equation modeling (SEM) and analytic hierarchy process (AHP) in supplier selection”.

Benchmarking: An International Journal, 19(1), Pp- 70-92.

40. Sivakumar, P., Ganesh, K., Anbuudayashankar, S.P., Punniyamoorthy, M., Lenny Koh, S.C.,

(2012),“Heuristic approach for balanced allocation problem in logistics: a comparative study”,

International Journal of Operational Research, Vol. 14, No. 3, 2012, Pp- 255 - 270

41. Punniyamoorthy, M., Mahadevan, B., Shetty, N.K., Lakshmi, G. (2011),"A framework for

assessment of brand loyalty score for commodities"Journal of Targeting, Measurement and

Analysis for Marketing 2011, Vol. 19, 3 / 4, Pp- 243–260

42. Manikandan, L., Thamaraiselvan, N., & Punniyamoorthy, M. (2011). “An instrument to assess

supply chain risk: establishing content validity.” International Journal of Enterprise Network

Management, 4(4), Pp- 325-343.

43. Parameshwaran, R., Srinivasan, P. S. S., &Punniyamoorthy, M. (2010). “An integrated approach

for performance enhancement in automobile repair shops”. International Journal of Business

Excellence, 3(1), Pp- 77-104

44. Punniyamoorthy, M., &Murali, R. (2010) “Identification of benchmarking service units through

productivity and quality dimensions”.International Journal of Business

PerformanceManagement, 12(2), Pp- 103-122.

45. Parthiban, P., M. Punniyamoorthy, K. Ganesh and G.R. Janardhana, (2009). “A model for

selection of suppliers by comparison of two clustering algorithms”. International Journal of

Applied Decision Sciences. 2: Pp- 422-443.

46. Parthiban, P., Punniyamoorthy, M., Ganesh, K., &RangaJanardhana, G. (2009).“A hybrid model

for sourcing selection with order quantity allocation with multiple objectives under fuzzy

environment”.International Journal of Applied Decision Sciences, 2(3), Pp- 275-298.

47. Punniyamoorthy, M., &Murali, R. (2009).“A framework to arrive at a unique performance

measurement score for the balanced scorecard”. International Journal of Data Analysis

Techniques and Strategies, 1(3), Pp- 275-296.

48. Parthiban, P., Punniyamoorthy, M., Ganesh, K., &RangaJanardhana, G. (2009). “Bidding process

and integrated fuzzy model for global sourcing based on customer preferences”. International

Journal of Electronic Customer Relationship Management, 3(1), Pp- 18-37.

49. Parameshwaran, R., Srinivasan, P. S. S., &Punniyamoorthy, M. (2009). “Modified closed loop

model for service performance management”.International Journal of Quality & Reliability

Management, 26(8), Pp- 795-816.

of 42

50. P. Mathiyalagan M. Punniyamoorthy, P.Parthiban(2009) “An integrated model for a class of

sourcing problem using multiple regression analysis and analytical hierarchy process.”

International Journal of Enterprise Network Management. Vol. 3, No. 4. Pp- 374-394.

51. Parthiban, P., Punniyamoorthy, M., Mathiyalagan, P., & Dominic, P. D. D. (2009). “A hybrid

decision model for the selection of capital equipment using AHP in conjoint analysis under

fuzziness”. International Journal of Enterprise Network Management, 3(2), Pp- 112-129.

52. Punniyamoorthy, M., &Murali, R. (2008). “Balanced score for the balanced scorecard: a

benchmarking tool”. Benchmarking: An International Journal, 15(4), Pp- 420-443.

53. Parthiban, P., Punniyamoorthy, M., Ganesh, K., &Parthasarathi, N. L. (2008). “Logical approach

for evaluation of supply chain alternatives”.International Journal of Management and Decision

Making, 9(2), Pp- 204-223.

54. Punniyamoorthy, M. Prasanna Mohan Raj.M (2007) “An empirical model for brand loyalty

measurement” Journal of Targeting, Measurement and Analysis for Marketing, 15, 222 – 233.

doi: 10.1057/palgrave.jt.5750044.

55. Prabha M, Punniyamoorthy M., Nivethitha. S (2019) “A Study on the Impact of Psychological

Empowerment on Motivation and Satisfaction among the Faculty Working in the Technical

Educational Institutions in India through based on Age and Work Experience difference”,

International Journal of Enterprise Network Management – Accepted for publication

56. Nafeesathul Basariya I, Punniyamoorthy M. (2018) “Data Analysis framework to predict the

behavior of macroeconomic indicators of countries”, International Journal of operations

research – Accepted for publication.

57. Nafeesathul Basariya I, Punniyamoorthy M. (2019) “A study on the Impact of macroeconomic

indicators on the stock price by relaxing the assumptions of stationary in time series data in

General Linear model”, International Journal of Enterprise Network Management – Accepted

for publication.

58. Prabha M, Punniyamoorthy M. (2018) “A model to quantify Psychological Empowerment of

Technical Institutional Faculty” Benchmarking: An International Journal. – Accepted for

publication.

59. NafeesthulBasariya, Punniyamoorthy, M. &Chitra Devi, N.(2018) “A framework to arrive at

Stationarity in Time Series Data”, Global Business and Economics Review–

Communicated.

60. Prabha M, Punniyamoorthy M., Nivethitha. S (2019), “Examining the bi-directional relationship

between Motivation and Satisfaction: Based on the impact of Psychological Empowerment”,

International Journal of Process Management and Benchmarking – Communicated.

http://link.springer.com/article/10.1057/palgrave.jt.5750044

http://link.springer.com/article/10.1057/palgrave.jt.5750044

of 42

61. Santhosh Kumar A,Punniyamoorthy M. (2018) “SVM as an agent performance evaluation tool -

Application in customer service industry”, International Journal of Business Performance

Management -Communicated.

Non – SCI Journals:

62. AntonetteAsumptha J, M. Punniyamoorthy and Roshan Rayen (2018) “Knowledge sharing

behaviour of physicians (Dentists) in Hospitals”, Global journal of Medical Research: K

interdisciplinary, volume 18 issue 1.

63. Jose Joy Thoppan, Punniyamoorthy M, Ganesh K, (2017), “Competitive model to detect stock

manipulation”, Communications of the IIMA, vol. 15(2).

64. AntonetteAsumptha J, M. Punniyamoorthy. (2017). “Compare and Contrast of Knowledge

Sharing of Academicians to Students-A Study in Private and Public Universities”. Journal of

Education and Learning. Vol. 11 (4) pp. 311-326. DOI: 10.11591/edulearn.v11i1.6580

65. M. Punniyamoorthy G. Lakshmi, &S. Chandramohan 2015). “A methodology for identifying

significant factors in supplier selection: a context based approach”, International Journal of

logistics and supply chain managementVol 4, No 2 Pp- 2319-9032.

66. M. Punniyamoorthy, G. Lakshmi, & S. Chandramohan(2015). “A methodology to prioritize the

constructs in supplier selection- An application in Engineering Industry,Global Journal for

Research Analysis, Vol 4(5), pp 349-351.

67. Punniyamoorthy, M., & Lavanya, V. (2015). “A conglomerate model for identification of the

interaction between job satisfaction and job performance in a service institution-a context bound

approach”. International Journal of Higher Education and Sustainability, 1(1), Pp- 66-87.

68. Murugesan Punniyamoorthy and Lavanya Vilvanathan (2013) “A study on job satisfaction in

service institution – context and model bound approach”, International journal of Logistics

Economics and Globalization, Vol.5, No.4, Pp- 269-291 (2013).

69. Mathiyalagan, P., Punniyamoorthy, M., Sezhiyan, D. M., &Meena, M. (2013). “An Empirical

investigation on the impact of supply effort management and supplier selection on business

performance using SEM approach”. Journal of Contemporary Research in Management, 5(2).

70. Kiruthika, A., Chandramohan, S., Punniyamoorthy, M., &Latha, S. (2013). “Fuzzy-DEA as a

diagnostic tool to measure and compare the performance of public and private banks including

foreign banks in India,”International Journal of Logistics Economics and Globalisation,

Volume 5, Issue 3.

71. Malairajan, R. A., Ganesh, K., Nallasivam, K., & Punniyamoorthy, M. (2012). “Comparison of

fuzzy C-mean clustering and 0-1 integer programming model for employee routing

http://www.inderscienceonline.com/loi/ijleg

http://www.inderscienceonline.com/toc/ijleg/5/3

of 42

problem”. International Journal of Value Chain Management, 6(4), Pp- 303-330.

72. Punniyamoorthy, M., & Thoppan, J. J. (2012). “Detection of stock price manipulation using

quadratic discriminant analysis”. International Journal of Financial Services

Management, 5(4), 369-388.

73. Punniyamoorty, M., & Shetty, N. K. (2011). “A study of customers’ brand preference pattern and

factors influencing brand preference in a commodity product”. International Journal of Indian

Culture and Business Management, 4(5), Pp- 523-542.

74. Parthiban, P., Mathiyalagan, P., Punniyamoorthy, M., & Dominic, P. D. D. (2010). “Optimisation

of supply chain performance using MCDM tool–a case study”. International Journal of Value

Chain Management, 4(3), Pp- 240-255.

75. Parthiban, P., Punniyamoorthy, M., Ganesh, K., &Janardhana, G. R. (2009). “Development and

assessment of modified VIKOR method for multi-criteria single sourcing in supply

chain”. International Journal of Business and Systems Research, 4(1), Pp- 94-116.

76. Parthiban, P., Punniyamoorthy, M., & Dominic, P. D. D. (2008). “An integrated model for

Optimization of production-distribution inventory levels and routing Structure for a multi-period,

multi-product, bi-echelon supply chain”. International Journal of Applied Management and

Technology, 6(2).

77. Parthiban, P., Punniyamoorthy, M., Janardhana, G. R., & Ganesh, K. (2008). “Supply chain

architectural framework and supplier relationship model for customer facing

business”. International Journal of Electronic Customer Relationship Management, 2(4),

Pp332-363.

78. P. Mathiyalagan M. Punniyamoorthy, S. Sudhakar (2009) “A supplier selection construct for

exploring supplier selection production in Indian manufacturing company”,Journal of

contemporary research in management, vol .1, No.4. Pp-123

79. M.Punniyamoorthy, Rani Susmitha and K.Ganesh (2012) “A casual model to assess the cardiac

patient satisfaction – A comparative study of speciality cardiac hospitals and multispecialty

hospitals”, International Journal of Information Logistics Economics and Globalization,

Volume 4, Issue 4.

Papers in National Academic / Professional Journals

80. “A scheduling Technique for the service institutions”, Journal of Industrial Engineering,

NITIE, Mumbai,

81. “Managing time ‘one should first plan the work and then work the plan”. Journal of Industrial

of 42

Engineering, NITIE, Mumbai,

82. “Economic justification of FMS”. Journal of Industrial Engineering, NITIE, Mumbai

Seminars & Conference Papers

83. “FCM based FSVM classifier using Fuzzy Index on credit risk evaluation”, International

conference on Business Analytics and Intelligence (ICBAI 2013), IIM, Bangalore, December

11 -13, 2013.

84. “DINLIP: Model to Solve Integrated Resource Allocation and Routing Problem with Bound and

Time Window”, International Conference on Modeling, Optimisation and Computing

(ICMOC 2012), Noorul Islam University, Kumaracoil, TamilNadu, India, April 10 – 11, 2012.

85. “Framework for Knowledge Management Need Assessment”, International Conference on

Modeling Optimisation and Computing- (ICMOC-2012),Procedia Engineering 38(2012) Pp-

3668 – 3690

86. “Service quality model to measure customer satisfaction”, Proceedings of the International

Conference on Delivering Service Quality: Managerial Challenges for the 21 St Century,

I.I.M., Ahmadabad. December, 1999

87. “A model to measure customer satisfaction”, Total Quality management, sponsored by UGC,

SNR Sons College, Coimbatore (1999).

Current Research Areas:

• Machine Learning algorithms and Applications

• Deep Learning

• Text Mining

• Recommender Systems

• Clustering Techniques

• Optimization Techniques

• Game Theory and applications

Books/Book Chapters

• K. Ganesh, Sanjay Mohapatra, R. A. Malairajan and M. Punniyamoorthy “Resource Allocation

Problems in Supply Chains” Emerald Group Publishing Limited, 2015. ISBN 178560399X,

9781785603990)

• Mohapatra, S., Ganesh, K., Punniyamoorthy,M., and Susmitha, R.” Service Quality in Indian

Hospitals – perspectives from an emerging market” Springer Publications, 2018.

• Production Management, Anna University, Chennai, MBA distance Education Program

of 42

• Data Analysis for Business Decision, getting ready for publication by Pearson Education, India.

• Solution Manual for the book PROJECTS: Planning, Analysis, Selection, Financing,

Implementation, and Review by Prasanna Chandra.

Extended Professional Responsibilities

Position in Academic Councils and Committees

• Member, NBA Accreditation Committee

• Member, UGC Accreditation Committee

• Member of Expert Committee by UGC for Accreditation at Arni University, Kangra.

• Head of Expert Committee by UGC for Accreditation at DAV University, Punjab.

• Member, AICTE Inspection Committee

• Member, Faculty Selection Committee, NIT Warangal

• Member, Faculty Selection Committee, NIT Calicut

• Member, Faculty Selection Committee, NIT Uttarakhand

• Member, Faculty Selection Committee, Central University – Hyderabad

• Member, Faculty Selection Committee, Central University – Thiruvarur.

• Chairman of Inspection Committee for Grant of Permanent Affiliation, Anna

University – Chennai.

Positions at NIT Tiruchirappalli

• Member of Advisory

• Committee on faculty Recruitment (ACoFAR) at NIT- Trichy.

• Member of Selection Committee for the posting of Registrar.

• Member of recruitment committee for faculty promotion and in handling issues

pertaining to NMR with Chairperson.

• Member of Equivalence Committee for framing recruitment rules at entry level for

Non- Teaching Staff.

• Member of grievance committee appointed by BOG

• Special recruitment drive for PwDs screening committee.

• Member of Committee for Stipend payment for M.Tech students.

• Member of interview committee for Apprenticeship Trainee.

Editorship in Journals – Current

• Editor in Chief, International Journal of Decision Making in Supply Chain and Logistics,

International Science Press, Serial Publications

• Guest Editor - Special Issue, Theme: “Special Issue on Application of Multivariate Techniques in

of 42

Decision-Making Models for Customer Service”, International Journal of Electronic Customer

Relationship Management, Volume 4 - Issue 4 – 2010, Inderscience Publishers.

• Member on the Editorial board, International Journal of Logistics and Supply Chain

Management, International Science Press, Serial Publications

• Member on the Editorial board, International Journal of Operations, Systems and Human

Resource Management, International Science Press, Serial Publications

Reviewer in International Journals

Elsevier: European Journal of Operations Research

Academic Journals (Lagos): African Journal of Business Management.

My Dissertation

Justification of Advanced Manufacturing Technology

Dissertations Guided

The Ph.D dissertations completed with me as Guide:

• Developing a Model to measure Brand Loyalty - M. Prasana Mohan Raj

• Unified heuristics for a class of sourcing problems in supply chain– P. Parthiban

• Supplier Selection through Structural Equation Modeling and fuzzy Logic - P. Mathiyalagan

• A Study on the Performance Management System - Murali R

• A study of customers brand preference pattern in commodity market with a special reference to

cement industry – Nandha Kishore Shetty

• Detection of Stock Price Manipulation: Developing an Effective Model For Detecting Trade

BasedMarket Manipulation – Jose Joy Thoppan

• A study on Service quality of cardiac hospitals in India: Model based approach - Rani Susmitha.

• Fuzzy Support Vector Machines for Credit Risk Evaluation, Sridevi.

• Framework on Job Satisfaction, Lavanya.

The Ph.D dissertations on going, with me as guide

• Opinion Mining using Fuzzy Support Vector Machine - A.Santhosh Kumar, Since 2012

• Knowledge Management in Health care industry - AntonetteAsumptha, since 2014

• Psychological Empowerment of Faculty - M.Prabha, since 2014

• Kernel Methods in SVM – S. Manochandar, since 2014

• Production and Operation Management – M. Ramanathan, since 2014

• Time Series Analysis - M.I Nafeesathul Basariya, since 2015

• Classification Techniques – M. Sivaguru, since 2015

• Spare parts Inventory Management – S. Kathirvel, since 2015

of 42

• Equilibrium selection in Non-zero sum two person game - Sarin Abraham, since 2015

• Classification Techniques – M. Vijayprabhagar, since 2015

• Sourcing in Materials Management – A. Maruthamuthu, since 2016

• Logistics Network Planning – B. Saravanar, since 2016

• Rural Banking – S. Balu, since 2016

• Service Level Determination in Supply Chain – R.Sundar, since 2016

• Comprehensive Frame work on Quality in Health Care – S. Niranjani, since 2017

• Activity Based Costing in Software Project Management – G. Kala Nisha, since 2018

In addition to the Doctoral Program, I have also guided over a 300 MBA projects and around 8 ME

Industrial Engineering Dissertations.

Examiner for Thesis

• Ph.D Thesis, IIT Dhanbad

• Ph. D. Thesis, Anna University, Chennai

• Ph. D. Thesis, JNTU, Hyderabad

• Ph. D. Thesis, Visvesvaraya Technological University,Belagavi, Karnataka.

• Ph. D. Thesis, Bharathiar University, Coimbatore

• Ph. D. Thesis, Sambalpur University, Sambalpur, Orissa

• Ph. D. Thesis, Alagappa University, Karaikudi

• Ph. D. Thesis, ManonmaniamSundaranar university, Tirunelveli

Software’s Developed

• Detection of Stock Price Manipulation using Genetic Algorithm and Neural Network

Executive Development Programs

Coordinated:

• “Nuances of Support Vector Machine”, Department of Management Studies, NIT,

Tiruchirappalli, October 5th – 7th 2012.

• “Data Mining and its Applications”, Department of Management Studies, NIT Tiruchirappalli,

October 2nd 2011.

• “Emerging Trends in Supply Chain and Changing Business Environment”, Department of

Management Studies, NIT Tiruchirappalli, Jan 22-23, 2011

• “MDP Program on Data Analytics for Business Decisions”, Department of Management

Studies, NIT Tiruchirappalli, Jan 21-26, 2006

of 42

Resource Person for:

• “Business Analytics and Intelligence”, Department of Computer Application, CIT Coimbatore,

April 24th , 2017

• “Data Analytics Workshop”, Department of Computer Science & Engineering, NIT

Tiruchirappalli, Jun 8th , 2012

• Training program for Promotee Executives, Bharat Heavy Electricals Limited (BHEL)

Tiruchirappalli, November 11-16, 2002

• Training program for Promotee Executives, Bharat Heavy Electricals Limited (BHEL)

Tiruchirappalli, October 21-26, 2002

• Training program for Executive Trainees, Bharat Heavy Electricals Limited (BHEL)

Tiruchirappalli, February 17, 1997.

Sponsored or consultancy Projects:

Sl. No. Title of the Project Funding Agency Period Remarks

(Completed/Ongoing)

1. Cognitive Based Curriculum

Development Tool For

Emerging Areas Of

Computer Engineering And

Management Studies For

Improving Teaching Learning

Process

University Grants

Commission (UGC)

Under Obama

Singh 21st Century

Knowledge

Initiative Grant,

Govt. of India

2013-

2016

Ongoing

2. Deciphering the Dynamic

Architecture Design from

Music and developing

software

MHRD, Govt. of

India Under

SCSP/TSP/ Sub

plan

2014-

2017

Ongoing(PATENT

PUBLISHED)Application

No: 201741002082

3. Data Mining - Opinion Mining DEITY 2015-

2020

Ongoing

Scholastic Record

Ph.D., Bharathidasan University, Tiruchirappalli

I.C.W.A.I. – Inter

The Institute of Cost and Works Accountant of India, Calcutta

M. Tech. — Industrial Engineering & Operations Research

Indian Institute of Technology, Kharagpur

B. Tech. — Production Technology

Madras Institute of Technology,Anna university, Chennai

of 42

B.Sc. – Mathematics

Rajah Serfoji Govt. College,Thanjavur

ANNEXURE I

Courses Taught

1. Machine Learning - This is an elective course at NIT, Tiruchirappalli, meant for students

specialising in Data analytics but has a lot of cross functional applications and hence opted by

students from Operations, Marketing and Finance Streams also. The course is designed to

provide an in-depth understanding of complex models and algorithms which is used for

predictive analytics.

2. Advanced Data Analytics – This is an elective course at NIT, Tiruchirappalli, meant for

students specialising in Data analytics. The course is designed to provide an in-depth

understanding of the modelling of data with special emphasis on Time series analysis and

clustering Techniques.

3. Game Theory and Applications - This is an elective course at NIT, Tiruchirappalli, meant for

students specializing in Operations but has a lot of cross functional applications and hence opted

by students from Marketing, Data Analytics and Finance Streams also. The course is designed to

provide an in—depth understanding of application of game theory in decision making and

strategy selection by an organization.

4. Data Analytics – This is an elective course at NIT, Tiruchirappalli, meant for students

specialising in Operations but has a lot of cross functional applications and hence opted by

students from Marketing and Finance Streams also. The course is designed to provide an in-depth

understanding of the modelling of data with special emphasis on multivariate techniques.

5. Logistics Management – This is an elective course at NIT, Tiruchirappalli, meant for students

specialising in Operations. The course is designed to provide an in-depth perspective into the

world of logistics management focusing on materials management, distribution management,

location and routing and scheduling, issues faced and customer service across various industries.

6. Production Planning and Control – This is an elective course at NIT, Tiruchirappalli, meant for

students specialising in Operations. The course is designed to provide a good theoretical base on

forecasting, facilities decision, aggregate planning, scheduling and process planning.

7. Supply Chain Management – This is an elective course at NIT, Tiruchirappalli, meant for

students specialising in Operations. The course covers the fundamentals of supply chain

management, supply chain planning, strategies, alliances, outsourcing, performance metrics,

planning and managing inventories, distribution management and strategic cost management in a

supply chain.

8. Production and Operations Management – This is a compulsory course at NIT,

Tiruchirappalli. The course is designed to provide a detailed view on the history of production

management, technology forecasting, environment, product design & development, process

planting, plant location issues, plant layout and material handling principles, job design, job

evaluation, purchasing and warehousing functions, vendor development and rating and value

analysis.

9. Project System Management – his is a compulsory course at NIT, Tiruchirappalli. The course is

designed to provide a detailed coverage on projects covering understanding of the environment,

lift cycle, feasibility analysis – market, technical, financial and economic, economic appraisal,

social cost, network techniques , multi project scheduling with limited resources, implementation,

of 42

funds planning, performance, budgeting and control, tendering and contract administration,

ecology and bio diversity issues and environmental impact assessment.

10. Fundamental of Financial Accounting – This is a compulsory course at NIT, Tiruchirappalli.

The course is designed to provide an introduction to concepts and conventions of accounting,

accounting standards, journal, ledger and trial balance, final accounts, P&L, balance sheet and

adjustments, depreciation, intangibles, inventory valuation etc.

11. Cost and Management Accounting – This is a compulsory course at NIT, Tiruchirappalli. The

course is designed to provide inputs on functional budget, cost ascertainment allocation and

control, reconciliation of cost & final account, process costing, working in process costing, joint

products, bye products costing, cost accounting methods - job, batch, and contract, standard

costing, utility of costing for managerial decision.

12. Quantitative Techniques– This is a compulsory course at NIT, Tiruchirappalli. The course is

designed to provide inputs on statistics, probability theory, binomial, Poisson and normal,

decision making under certainty, uncertainty and risk, sampling and sampling distribution,

estimation, testing hypotheses and non-parametric methods.

of 42

SUMMARY SHEET

Name of Applicant DR. M. PUNNIYAMOORTHY

Date of Birth 07-05-1962 Age

(as on 29-Jul- 2019) 57 years 02 months

Correspondence

Address

Professor,

National Institute of

Technology,

Tiruchirappalli,

Tamilnadu,

India -620 015

Permanent Address

Door No: 15,

S. S. Nagar,

Near R.R. Nagar,

Thanjavur,

Tamilnadu,

India-613 005

Official Phone No 0431-2503032 Mobile No +91-9443866660 (Office)

+91-9489066223 (Personal)

Email id [email protected] Alternate Mail id [email protected]

Current Position Professor Date of appointment

of current position 23 April 2007

Current Affiliation National Institute of Technology,Tiruchirappalli, Tamil Nadu,

India-620 015

Work Experience

Total Work Experience 32 Years 03 Months

Teaching Experience as Professor 12 Years 03 Months

Administrative Experience 13 Years 02 Months

Research

Contributions

Number of Journal Publications (in

UGC approved list) 68

Number of Presentations in

International Conferences 05

Number of Books/Proceedings Published 03 books

Number of Patents Awarded 01

Sponsored research (Total Value) ₹ 98 Lacs

No. of Ph.D. Completed 10

No. of Ph.D On-going 17

mailto:[email protected]

mailto:[email protected]

of 42

PATENT PUBLISHED

A LOGIC TO DECIPHER THE DYNAMIC ARCHITECTUR FROM MUSIC

AND VICE-VERSA (App. No. : 201741002082)

The efforts to discover the logic of defreezing the music in architecture started from Vitruvius

(80-15 BC) and continued in the modern era by IannisXenakis among many others. As a

continuation and also to defreeze the architecture in music, a process has been laid out. At

first, rhythm, texture, harmony, geometry, proportion and dynamics are considered as a base

to evolve the aural parameters and the corresponding visual parameters. These parameters

involved in visual format (Architecture) and aural format (Music) are used to form logic to

decipher the music from architecture and vice-versa. In the case of frontal elevation of a

building design, visual perception involved the movements in x-direction relating to the

visual scanning the length, and y-direction relating to the visual scanning the height, and in

the z-direction relating to the visual scanning the depth. As in the visual, the aural perception

includes the length of time, the height of frequency and the depth of loudness. Hence the

visual and the aural perception have complimentary dimensions. With the axes scaling as the

base, for both aural and visual parameters, a comparison emerged out as: Timbre in aural

format to the ground level separation in visual format, the chords in a musical composition to

the vertical members of the visual design, the periodicity in a visual design to the form of

musical composition in aural format. Thus, the aural parameters are extracted from the grid

(visual parameters in the axes) to compose a music and a vice-versa process of extracting the

visual parameters from the grid (aural parameters in the axes) to arrive at an architectural

design. This process resulted in a development of the logic for an evolutionary algorithm. The

logic is validated and found feasible.

of 42

CURRENT RESEARCH CONTRIBUTION

Text Mining using Machine Learning Techniques

The classification of opinion based on customer reviews is a complex process owing to high

dimensionality. This research objective is to select the minimum number of features to classify

reviews effectively. The tf-idf and Glasgow methods are commonly for feature selection in

opinion mining. We propose two modifications to the traditional tf-idf and Glasgow expressions

using graphical representations to reduce the size of the feature set. The accuracy of the proposed

expressions is established through the support vector machine technique. Also, a new framework

is devised to measure the effectiveness of the term weighting expressions adopted for feature

selection. Finally, the strength of the expressionsis established through evaluation criteria and

effectiveness. The modified term weighting expressions isadopted for the extraction of the

minimum number of prominent features required for classification, thus enhancing the

performance of the Support Vector Machine.

Publication:

Manochandar, S., Punniyamoorthy, M, (2018) “Scaling Feature selection method for

enhancing the classification performance of support vector machines in text mining”,

Computers & Industrial Engineering, Volume 124, October 2018, Pages 139-156.

Performance enhancement of a new user similarity model in collaborative filtering

Collaborative filtering (CF) is a widely utilized automated product recommendation technique in

e-commerce. The CF-based recommender system (RS) depends on similarities among users or

items determined by a user-item rating matrix. The similarity is calculated using conventional

distance measures or vector similarity measures such as Pearson’s correlation, cosine similarity,

Jaccard similarity, or Spearman rank correlation. However, these methods are not very effective

owing to the sparse matrix. To improve the performance of CF- based RS, a modified similarity

measure is introduced based on Proximity-Impact-Popularity (PIP). In conventional PIP the

magnitude of each component is unequal, resulting in unequal component weights in different

scenarios. To overcome this problem, our proposed PIP measure has a range of 0-1. Moreover, a

mean-based prediction formula is typically used to predict the rating, which only considers the

of 42

user-related deviation. Therefore, we also propose a more accurate modified prediction

expression, which is also applicable for unavailable rating and prediction for new user / item with

no records. The proposed method is tested using datasets such as MovieLens, Netflix, Eopinion,

CiaoDVD, MovieTweet, and FlimTrust. The performance criteria adopted for this study are the

mean absolute error, root mean squared error, precision, recall, and F-measure. Our results are

compared with those from existing methods, which reveals that our proposed framework provides

better results for sparse matrix than the conventional methods. Finally, the statistical test is

conducted for the cold start problem our proposed method provides a significant result than the

conventionalmethods.

Publication:

Manochandar, S., Punniyamoorthy, M, and Jeyachitra R.K. (2018) “An Improved

similarity measure for collaborative filtering”,Information Science(Under Review)

Opinion Mining using Support Vector Machine with improved kernel functions

To extract opinion from text documents various machine learning algorithms are used and

Support Vector Machine (SVM) is one among them. The SVM is more popular because of its

efficient classification of non-linear data using Kernel trick (Kernel function) which implicitly

transforms the input to a higher dimensional vector space, thereby data can be classified linearly.

In this research, the dissimilarity kernel function is proposed to handle the sparse data. The new

kernel functions are adopted to classify opinions from customer feedback of B2C (Business to

Consumer industry) contact center. Also, the performance of the proposed method is evaluated

the contact center agent from the customer feedback data.

Publication:

Punniyamoorthy, M. & Santhosh Kumar A. (2015). “Opinion Mining of Movie Review

using new Jaccard dissimilarity Kernel function”.International Journal of Pattern

Recognition and Artificial Intelligence. (Under Review).

SVM as an agent performance evaluation tool - Application in customer service

industry

In the present digital world, the rapid growth in unstructured text data prompts the business to

revamp the organization strategy based on the knowledge discovered from the data using text or

opinion mining. To extract opinion from text documents various machine learning algorithms are

used and Support Vector Machine aka SVM was one among them. The SVM was more popular

because of its efficient classification of non-linear data using Kernel trick (Kernel function)

of 42

which implicitly transforms the input to a higher dimensional vector space, thereby data can be

classified linearly. In this paper, we have applied dissimilarity kernel function which can be used

when the data are sparse. In our study, we have evaluated the new kernel functions to classify

opinions from customer feedback of B2C (Business to Consumer industry) contact centre and

evaluate the performance and ranked the contact centre agent from customer feedback data.

Publication:

Punniyamoorthy, M. & Santhosh Kumar A. (2019). “SVM as an agent performance

evaluation tool - Application in customer service industry”.International Journal of

Business Performance Management. (Under Review).

A new mean to identify the number of clusters through Self –Organizing map

Self-organizing map (SOM) is a popular technique for data reduction and data clustering. In

conventional SOM, the weights of each node are created and assigned randomly. We proposed a

procedure to create the initial weights and way to assign those weights to the grid. Also, we also

proposed a new way to determine the number of clusters. The performance of the proposed

algorithm and the existing algorithm of SOM is compared against the performance criteria

regarding Accuracy, Number of iterations and Elapsed time. It is found that the proposed

algorithm excels in all criteria.

Publication:

Vijaya Prabhagar, M., Punniyamoorthy, M, (2019) “Means to enhance the performance

of Kohonen Self-Organizing map”, Neurocomputing (Communicated).

A modified rough k-means clustering algorithm

The soft clustering technique in the field of data mining has recently been enriched by the

introduction of the rough k-means clustering algorithm along with the fuzzy c-means

clustering algorithm. This technique is being applied in several areas for its ability to handle

uncertainty in a dataset. Even though its usage is important from the perspective of handling

uncertainty in the dataset, its performance is put under continuous scrutiny. The cluster

initialization function is one important function that affects the good clustering performance

of the rough k-means algorithm. Another parameter that determines the clustering

performance is the weight parameter used in calculating cluster means. In this paper these

two important parameters are investigated in detail and it is found that there is room to

of 42

improve this algorithm through modifications. For this purpose, a novel initialization

procedure is proposed to overcome the shortcomings of the random initialization function of

the rough k-means algorithm. A formula for calculating the dynamic weight that is to be

used in calculating the cluster means in the rough k-means algorithm is also proposed. The

proposed methods help in increasing the clustering effectiveness which is demonstrated

using the large synthetic, forest cover, microarray, bank marketing, Coil 2000, and telecom

datasets. The experimental results show that our modified algorithm has better clustering

performance than the existing rough k-means clustering algorithm.

Publication:

Sivaguru, M. & Punniyamoorthy, M. (2017), “A Modified Rough K– Means

Clustering Algorithm”,Pattern Recognition (Under Review).

A new initialization and performance measure for the Rough k-means Clustering

In this research, an initialization method is proposed to compute initial cluster centers for Peter’s

rough k-means algorithm . A new means to choose appropriate zeta values in Peters refined rough

k-means clustering algorithm is proposed. Also, we have introduced a new performance measure

S/T index. The performance criteria like Root Mean Square Standard Deviation, S/T index and

Running time complexity are used to validate the performance of the proposed and random

initialization with Peters refined rough k-means clustering algorithm. In addition, other

initialization algorithms like Peters k-means++, Peters Π, Bradley and Ioannis’ are also compared

Publication:

Vijaya Prabhagar, M., Punniyamoorthy, M, (2019) “A new initialization and performance

measure for the rough k-means clustering”, Soft Computing. (Under Review).

A New Seed and Performance Measure for k- Means Clustering

Conventional k-means clustering algorithm takes initial points to compute centroid each time in

a random manner. We propose twonew initialization procedures for the k-means clustering

algorithm to obtain the consistent sum of squared error. This algorithm is applied for various

benchmark data sets, and the results are compared with the results obtained in conventional k-

of 42

means and k-means++ clustering algorithm. It shows the error value obtained by our proposed

algorithm is consistent and it provides better results for most of the cases. We develop a

composite performance measure for the analysis of the algorithm. We introduce the technique to

determine the number of replications in the evaluation of the performance measure of the

datasets. The performance measure and its comparative analysis of the proposed algorithms with

conventional k-means and k-means++ algorithms are presented. Also, the validity measure such

as Dunn index and Silhouette index are included.

Publication:

Manochandar, S., Punniyamoorthy, M, (2018) “Development of new seed with modified

validity measures for k-means clustering”, Computers & Industrial Engineering.

(Under Review)

Equilibrium selection in Non-zero sum two person game

A non-zero sum bi-matrix game may yield numerous Nash solutions while solving the game. The

player will then have to make a selection of a good Nash equilibrium among the many options.

This poses a dilemma for the players. In this research work, three methods have been proposed to

select a good Nash Equilibrium. The first approach helps in identifying the most payoff-dominant

Nash equilibrium while the second method selects the most risk dominant Nash equilibrium. The

third method combines risk dominance and payoff dominance by giving due weight to the two

criterion. This provides the player with the best Nash Equilibrium chosen over the other Nash

Equilibria thus easing out the selection process for the players

Publication:

Sarin Abraham, Punniyamoorthy, M. and Jose Joy Thoppan (2018) “Selection of Nash

Equilibrium in Two-Person Non-Zero Sum Game - A Multi-Criteria Approach”.

European journal of Industrial Engineering (Under Review).

A development in the existing Non-linear model and to study its impact on the Nash

Equilibrium in a two-person non-zero sum game

A non-zero sum two-person game can be formulated as a non-linear program problem for finding

the Nash equilibrium. Although intensive research has been done in developing methods for

solving such non-linear problems, very less work has been done in modifying the existing model

of 42

in order to generate a more refined Nash solution. The study focuses on modifying the nonlinear

programming model by incorporating some additional constraints and analyzing if the altered

model would generate a better result. The utility of the additionalconstraintsis discussed, in terms

of expected payoff and actual payoff, for different problem situations.

Publication:

Sarin Abraham, Punniyamoorthy, M. (2019) “A developmentin the existing Non-linear

model and to study its impact on the Nash Equilibrium in a two-person non-zero sum

game”. International journal of enterprise network management (Under Review).

Deciphering the frozen music in building architecture and vice- versa Process

The efforts to discover the logic of de-freezing the music in architecture started from Vitruvius

(80 -15 BC) and continued in the modern era by Iannis Xenakis among many others. As a

continuation and also to de-freeze the architecture in music, a process has been laid out. At first,

rhythm, texture, harmony, geometry, proportion, and dynamics are considered as a base of

complementary aural and visual formats, to evolve the aural parameters and the corresponding

visual parameters. These parameters involved in visual format (Architecture) and aural format

(Music) are used to form logic to decipher the music from architecture and vice-versa. With the

axes scaling as the base, for both aural and visual parameters, a comparison is emerged out. Thus,

the aural parameters are extracted from the grid (visual parameters in the axes) to compose a

music and a vice-versa process of extracting the visual parameters from the grid (aural parameters

in the axes) to arrive at architectural design. This process resulted in the development of an

algorithm

Publication:

Anu Sendhil, Muthukkumaran, K, Punniyamoorthy, M, Veerapandian, S. A., &

Sangeetha, G, (2017), “Deciphering the frozen music in building Architecture and Vice-

Versa process”,Multi Media Tools and applications (Under Review).

Transformations Involved in Visual and Musical Grid

Every architectural design is a combination of various geometrical forms. The generated forms

are from the basic shapes like circle, square, triangle and the like. The whole geometrical shapes

of 42

transform. The transformed volumes are then organized to form the building design. Similarly, in

music, varying musical notes based structures transform to form a musical composition. This

paper deals about the transformations both in architecture design deciphered from music and

music de-frozen from building architecture design.

Publication:

Anu Sendhil, Muthukkumaran, K, Punniyamoorthy, M, Veerapandian, S. A., &

Sangeetha, G, (2018), “Transformations Of Architectural And Musical Forms Involved In

Visual And Musical Grid”, Journal of New Music Research (Communicated).

Fuzzy Support Vector Machines for Credit Risk Evaluation

Credit risk assessment has gained importance in recent years due to the global financial crisis and

credit crunch. Financial institutions, therefore, seek the support of credit rating agencies to predict

the ability of creditors to meet financial persuasions. The purpose of this paper is to construct a

neural network (NN) and fuzzy support vector machine (FSVM) classifiers to discriminate good

creditors from bad ones and identify the best classifier for credit risk assessment.This study uses

an artificial neural network, the most popular AI technique used in the field of financial

applications for classification and prediction and the new machine learning classification

algorithm, FSVM to differentiate good creditors from bad. As membership value on data points

influence the classification problem, this paper presents the new FSVM model. The instances

membership is computed using fuzzy c-means by evolving a new membership. The FSVM model

is also tested on different kernels and compared,and the classifier with the highest classification

accuracy for a kernelis identified.The paper identifies a standard AI model by comparing the

performances of the NN model and FSVM model for a credit risk data set. This work proves that

that FSVM model performs better than the backpropagationneural network.The proposed model

can be used by financial institutions to accurately assess the credit risk pattern of customers and

make better decisions.This paper has developed a new membership for data points and has

proposed a new FCM-based FSVM model for more accurate predictions.

Publication:

Punniyamoorthy, M., & Sridevi, P. (2016).” Identification of a standard AI based

technique for credit risk analysis”. Benchmarking: An International Journal, 23(5),

Pp- 1381-1390.

of 42

Evaluation of an FCM-based FSVM classifier using fuzzy index

Support vector machine (SVM), the new machine learning classification algorithm, has shown

good generalization capability in binary classification problems. But, on datasets with outliers or

noises, SVM has not shown good classification performance. As fuzzy support vector machine

can significantly reduce the effect of outliers or noises, this study has adopted FSVM for model

analysis. As membership value on data points influence model performance, fuzzy C-means

algorithm was used to evolve membership values on different fuzzy index values. With the new

formulation of the membership function, new membership values are created and used to run the

FSVM model. The computational process of FSVM model on RBF kernel is tested by grid search

for different combinations of parameters,and the performance of the model on different indices

was observed. The classifier with the highest classification accuracy for a particular index and

kernel parameters is identified as the best classifier for the dataset.

Publication:

Punniyamoorthy, M., & Sridevi, P. (2017). “Evaluation of a FCM-based FSVM classifier

using fuzzy index”. International Journal of Enterprise Network Management, 8(1),

Pp- 14-34

Application of machine learning techniques to predict carotid atherosclerosis

The focus of this paper is to examine factors associated with carotid atherosclerosis in

patients with impaired glucose tolerance (IGT) and to predict the rapid progression of

carotid intima-media thickness (IMT). The proposed machine learning methods performed

well and accurately predicted the progression of carotid IMT. The linear support vector

machine, non-linear support vector machine with a radial basis kernel function, multilayer

perceptron (MLP), and the Naive Bayes method was employed. A comparison of these

methods was conducted using the Brier score, and the accuracy was tested using a confusion

matrix

Publication:

Maruthamuthu A, Punniyamoorthy M, SwethaManasaPaluru, SindhuraTammuluri (2018)

“Prediction of carotid atherosclerosis in patients with impaired glucose tolerance – A

performance analysis of machine learning techniques” International Journal of

Enterprise Network Management. (In Print)

Comparative study of machine learning techniques for breast cancer diagnosis

of 42

The number of new cases of female breast cancer was 124.9 per 100,000 women per year.

Similarly, deaths were 21.2 per 100,000 women per year. It calls for an urge to increase the

awareness of breast cancer and very accurately analyze the causes which may differ in minute

variations. This is why the application of computation techniques are widely growing to support

the diagnostic results. In this paper, we present the application of several machine learning

techniques and models like a neural network, SVM is used to quantify the classifications. The

methods that are most reliable, accurate and robust are emphasized. It gives a plethora of

explorations into the research field for developing predictive models. To achieve higher

reliability on the data, we present the comparison of various Machine Learning techniques on a

dataset that is available on the website Kaggle

Publication:

Ganapathy G,Sivakumaran N, Punniyamoorthy M, Surendran R, SrijanThokala (2018)

“Comparative study of machine learning techniques for breast cancer

identification/diagnosis” International Journal of Enterprise Network Management,(In

Print)

Improving the Prediction Accuracy of Low Back Pain using MachineLearning

techniques

Application of machine learning algorithms in the healthcare industry has been increasingby

many folds. Low back pain has caused problems to many persons all around the world. An early

treatment or detection of whether a person has the symptoms about low back pain can help faster

medication and treatment of the patient and help them with getting their medical condition

degraded. This paper focuses on four different machine learning algorithms viz. SVM, Logistic

Regression, K-NN and Naïve Bayes which can be used to predict whether a person is suffering

from low back pain or not. Finally, the modification is carried out in Naïve Bayes algorithm to

enhance the performance of the algorithm. The Kaggle dataset is adopted to validate the machine-

learning algorithm. The accuracy of each algorithm is compared.

Publication:

Ganapathy G, Sivakumaran N, Punniyamoorthy M, Tryambakchatterjee, Monisha Ravi

(2018) “Improving the prediction accuracy of low back pain using machine learning

through data pre-processing techniques”International Journal of Medical engineering

and informatics. (Accepted)

of 42

Analysis and Assessment of divergence of final offers in negotiation with reference to

Gamma and Beta distribution

A Final Offer Arbitration game involves two parties trying to resolve a dispute with the help of

an outside negotiator. The two parties submit an offer to the arbitrator, who then selects one of

the offers closer to his assumption of a fair settlement. This game can be modeled as a zero-sum

game, where the offer that each party proposes represents the strategies available for the two

players of the game. Although the arbitrator’s choice is not known to either of the players, the

distribution that the arbitrator’s offer follows is known to them. Taking an appropriate guess of

the distribution that the arbitrator’s fair settlement may follow, both the parties propose an offer

around the median of that distribution. Many labor relationship managers claim that such an

approach of the two parties will lead to an automatic convergence of the two proposals, but game

theorists have shown that there is always be a divergence between the two equilibrium strategies.

In this research work, the divergence between the equilibrium strategies hasbeen computed for

two new distributions namely Gamma and Beta distribution. The calculateddivergence for

Gamma and Beta distribution are then compared with the known divergence of other

distributions.

Publication:

Sarin Abraham, Punniyamoorthy, M. (2019) “Analysis and assessment of divergence of

final offers in negotiation with reference to Gamma and Beta distribution”. Annals of

Operations Research(Communicated).

Influence of fuzzy index parameter on FSVM classifier performance

Support vector machine (SVM), a machine learning algorithm used extensively for pattern

analysis and recognition, is found sensitive to outliers and noise. Fuzzy support vector machine

(FSVM) has been used in many applications as a most prominent technique by researchers to

overcome the sensitivity issue faced by SVM and for its goodgeneralization performance. In this

research, a method to justify the performance of FSVM classifier by showing the influence of

fuzzy index m on membership function of the model has been proposed. In the first phase of the

study, an algorithm to find the optimal fuzzy index using fuzzy C-means (FCM) and to avoid

testing all fuzzy index values on the FSVM model has been proposed. This process can reduce

the operational complexity of the model. In the second phase of this study,an FSVM algorithm to

of 42

incorporate new membership function is proposed. The model is tested on six different datasets

and kernel functions,and the kernel with the highest classification accuracy is identified as an

efficient kernel for the applied dataset. The experimental results on the chosen fuzzy index have

proven that the proposed alternate methodology enhances classifier accuracy compared to other

research findings. Hence, the model could be applied to diverse fields of FSVM applications.

Publication:

Sridevi, P., Punniyamoorthy, M., & Senthil Arasu B. (2017). Influence of fuzzy index

parameter on new membership function for an efficient FCM based FSVM classifier.

Journal of the National Science Foundation of Sri Lanka. 45(4) pp 367 -379.

WORKING PAPERS

Dynamic fuzzy clustering using cumulative marginal error (cost curve)

The management of customer dynamics is critical for any organization that aspires to build an

effective customer relationship with customers. In this study, our objective is to improve the

dynamic customer segmentation effectiveness using the dynamic fuzzy c-means clustering

algorithm. The dynamic fuzzy c-means clustering algorithm is the most commonly used

algorithm in the literature for doing dynamic customer segmentation. We propose two

modifications to the existing dynamic fuzzy c-means clustering algorithm; the first one uses the

graphical representations to identify the changes in the cluster structure. Secondly, a

modification to the current structure strength formula is proposed to determine the number of

new clusters needs to be created. The effectiveness of the proposed expressions is established

through the sum of squared error. The modified approaches are tested using the online retail

dataset for dynamic customer segmentation comparing with the existing method. The modified

approach improved the effectiveness of customer segmentation results.

Performance enhanced dynamic fuzzy clustering algorithm

The effectiveness of dynamic customer segmentation with new customer data update is difficult

due to the certain shortcomings of the existing dynamic fuzzy c-means clustering algorithm. In

this study, our objective is to improve the effectiveness of dynamic customer segmentation. By

doing so the customers’ existing similar buying pattern, perished buying pattern and emerging

of 42

new buying pattern can be identified. In this process, we propose modifications to the DFCM

algorithm, using the clustering validity index to identify the changes in the cluster structure, i.e.

creation of new clusters, movement of existing clusters and elimination of existing clusters. The

clustering effectiveness of the proposed methods is validatedusing the sum of squared error of

clustering. Besides, we analyse the DFCM algorithm concerning its function of the movement

of clusters, the creation of new clusters and its structural strength expression. Finally, the

strength of the proposed method is evaluated by its ability to find new clusters, doing the

movement of existing clusters and the elimination of theexisting clusters. Based on our

experimental results, it is shown that the proposed methods can be more effective than the

existing DFCM algorithm thus improving the dynamic customer segmentation effectiveness.

PSO clustering with a different perception

In the Standard PSO (SPSO) algorithm, normal random variate is used to create the coordinates

of the particle. It considers each coordinate separately and is assumed to follow the normal

distribution individually. In PSO clustering algorithm, the particle is assumed as a vector of

cluster centres. The same technique from SPSO is followed to assign the initial particle

locations for PSO clustering. Usually, the cluster centres are created from the data points,and

their mean and standard deviations of each variable are used to createeach coordinate of the

particle randomly. Instead of assuming a normal distribution for individual coordinates of the

particle, we propose the multi normality assumption for creating a segment of the particle. Also,

we added a new dimension to the velocity update. We proposed a family best concept in

addition to the existing bests (global best, and personal best). Each particle in PSO helps to form

the cluster. Based on it, we cluster the particles which help to form a cluster are grouped

similarly every other particleare grouped. From them, we find the family best which in turn

helps to attain a better clustering performance.

Prediction of heart disease using improved K-nearest neighbor and Naïve Bayesian

approaches

Heart disease accounts for the highest toll of human lives, compared to other diseases. In spite

of the efforts taken by Government on a continuous basis both in cities and rural areas, the death

rate is high as people could not reach hospitals in time or not knowing the seriousness of the

disease. What people live in cities could get access to good multi-specialty hospitals and take

treatment in time to the extent possible. Whereas Patients in remote areas could not have access

to advanced facilities and treatments despite advancements in Treatments of diseases, have been

of 42

witnessed nowadays in the medical field. Heart patients who live in cities to some extent subject

themselves to monitoring of their health on a regular basis. But patients who live in rural areas

do not get opportunities for continuous check-ups and hence risk life. Therefore, it is the

necessity to think of certain new methods of monitoring the patients in rural belts. To support

this cause, the new technology - machine-to-machine (M2M) technology can be utilized for

monitoring of heart disease patients. Patients medical condition can be measured periodically at

home and stored for future analysis. Even then, it is difficult to perform complex tests which

need a physician’s help. With the help of data mining techniques, heart disease prediction can

be improved. There are some algorithms that havebeen used for this purpose like Naive Bayes,

and k-Nearest Neighbor (KNN). This study aims to use data mining techniques in heart disease

prediction, with the help of Clinical Decision Support System. KNN is used with the parameter

weighting method to improve accuracy. Four normalization techniques are adopted to improve

the accuracy of the classification techniques.

Fuzzy Matrix for a Zero-Sum Game with Varied Values α -Cut and Lambda, λ

The payoff matrix for a bimatrix game cannot always be determined with certainty. Under such

uncertainty condition, it may be possible to give an interval for the payoffs, thus representing

the payoff matrix with fuzzy numbers. Unlike most of the papers where the fuzzy numbers were

assumed to follow a symmetrical triangular distribution, in this paper we have introduced the

concept of the fuzzy numbers following an asymmetrical triangular distribution. Since an

asymmetrical triangular distribution is used, two additional parameters, α1 and α2, representing

the rejection region on either side of the mode is being introduced. The parameters α, and α1 /

α2, representing the acceptance region and the either side of the rejection region, is used to

determine the lower and upper limit for the fuzzy numbers. In the defuzzification process, the

parameter λ, representing the weight assigned to the upper fuzzy matrix, is also accustomed to

variations. The sensitivity analysis of the Nash equilibrium, for different values of α, α1, α2, and

λ is checked to see which combination yields a better result.

of 42

Courses Taught Presently and their Contents

Course 1 Machine Learning

Supervised Learning

• Bayesian Classification: Naive Bayes. Rule-Based Classification,

• Artificial Neural Network: Classification by Backpropagation.

• Support Vector Machines,

• Associative Classification,

• K-NN classifier, Case-Based Learning,

• Rough set, Fuzzy set approaches, Hidden Markov models.

Unsupervised Learning-I

• Clustering Methods K-Means, K-Medoids.

• Fuzzy C-Means Clustering.

• Hierarchical Methods:Agglomerative and Divisive.

Unsupervised Learning-II:

of 42

• Grid-Based Methods: STatisticalINformation Grid,

• Model-Based Clustering Methods: EM algorithm,

• Self – Organizing Map.

• Outlier Analysis.

Soft Computing Components:

• Neighborhood-based algorithms, Simulated Annealing, Tabu search.

• Population-based algorithms- Evolutionary computation: Evolutionary

programming and strategies, Genetic algorithms, Genetic

programming,

• Differential evolution. Swarm Intelligence: Ant colony optimization,

Particle swarm optimization

Course 2 Game Theory & Applications

Introduction

• Trees – Game Trees – Information Sets;

• Choice functions and Strategies – Choice Subtrees;

• Games with Chance moves – Theorem on Payoffs;

• Equilibrium N – tuples of Strategies; Normal Forms.

Two - Person zero – Sum Games

• Saddle Points; Mixed Strategies – Row values and Column Value,

Dominated rows and columns;

• Small Games – 2 x n and m x 2 games;

• Symmetric Games – Solving Symmetric Games.

Non-zero- sum games

• Non-cooperative Games – Mixed Strategies, Max-min Values,

• Equilibrium N – tuples of Mixed Strategies,

• A Graphical Method for Computing Equilibrium Pairs;

• Solution Concepts for Non-cooperative Games – Battle of the Buddies,

Prisoner’s Dilemma, Another game, Super games;

• Cooperative Games – Nash Bargaining Axioms, Convex Sets, Nash’s

Theorem, Computing Arbitration Pairs.

N-Persons Cooperative Games

• Coalitions – The Characteristic function, Essential and Inessential

Games; Imputations – Dominance of Imputations, the Core,

• Constant – Sum Games, A Voting Game;

• Strategic Equivalence - Equivalence and Imputations, (0,l) -Reduced

Form, Classification of Small Games;

• Two Solution Concepts - Stable Sets of Imputations, Shapley Values.

Applications

• Voting – Voting Rules, Paradoxes, Strategic Manipulations;

https://en.wikipedia.org/wiki/Differential_evolution

of 42

Bargaining

• Nash Bargaining Solution, Ultimatum game, alternating – offers game,

Threat Points, Bargaining Shares; Auction.

Course 3 Basic Data Analytics

Multiple Regression

• Assumptions for General Linear Regression Model,

• Ordinary Least Square (OLS) Approach – measures of fit,

• Statistical inferences – Hypothesis testing and interval estimation

• Data cleaning – Outliers and influential observations

Variable Selection

• Retaining of predictors – Forward, backward, stepwise, sequential and

all possible subsets

• Dummy regressions and conjoint analysis,

• Multicollinearity

Discriminant Analysis – I

• The Two-Group problem –Variable contribution

• The case of Discrete Variables

• Logistic regression, Error rate estimation.

Discriminant Analysis – II

• The K groups problem, Error rate estimate in multiple groups,

• Interpretation of multiple discriminant analysis solutions.

Factor Analysis

The basic model, Extraction of factors

• Principal factor

• maximum likelihood method,

• factor rotation – orthogonal, oblique rotations,

• factor score,

• Interpretations of factor analysis solutions.

Course 4 Advanced Data Analytics

Principal Component Analysis

• Extracting Principal components

• Test of significance

• Component scores.

Time Series Analysis

• Pre-Processing of Data- Outlier Analysis

• Introduction to Stationarity – Correlogram: Auto Correlation; Partial

of 42

Auto Correlation; Q-Stat

• Checking for Stationarity- Unit Root Test: Dicky Fuller Test,

Augmented Dickey-Fuller

• Analysis of Residual- Durbin Watson Test; Run Test

• Auto-Regressive Integrated Moving Average Models- AR(p), MA(q),

ARMA(p,q) and ARIMA(p,d,q)

• Estimation of Parameters for ARIMA – Levenberg Marquardt Method;

Gauss-Newton Method; Berndt, Hall, Hall and Hausman Method

• AutoRegressive Conditional Heteroscedasticity (ARCH(p))

• Generalized AutoRegressive Conditional Heteroscedasticity

(GARCH(p,q))

Multidimensional scaling

• Proximities, and Data collection,

• Spatial map-metric,

• Non-metric data,

• Joint space analysis.

• Naming and interpreting the dimension,

• Attribute-based perceptual mapping using factor analysis,

• Spatial map using preference data through internal analysis and

external analysis.

Cluster Analysis

• Similarity measures,

• Hierarchical and partitioning methods,

• Graphical methods, Assessing cluster solutions and implementation

Penning Bookon Data Analytics

The book titled on “Data analytics for Decision Making” is prepared for

publication. It deals with the multivariate analysis and its applications in

engineering and management fields. Each multivariate analysis techniques are

explained with the detailed flow charts and solved examples.

The content of the book is as follows:

Chapter

1 Multiple Regression

of 42

1.1. Introduction to Multiple Regression

1.2 Assumption for Ordinary Least Square

1.3 Analysis of Multiple Regression Techniques

1.4 Test of Significance of the model

1.4.1 ANOVA

1.4.2 t-test

1.4.3 Co-efficient of determination

1.5 Arriving at an optimum model

1.5.1 Forward Regression

1.5.2 Backward Regression

1.5.3 Stepwise Regression

1.5.4 Subset Regression

Solved Example

Chapter

2 Multi Collinearity

2.1 Diagnosis of Multi-Collinearity

2.2 Variance in Inflation Factor (VIF)

2.3 Condition Index (CI)

2.4 Ridge Regression

Solved Example

Chapter

3 Discriminant Analysis

3.1 Introduction

3.2 Assumptions

3.3 Derivation of Fisher Discriminant Analysis

3.4 Classification rules

3.5 Calculation of misclassification error

3.6 Statistical Tests

3.7 Interpretation of the attributes concerning Discriminant axes

of 42

3.8 Variable contribution

3.8.1 Wilks’ Lambda

Solved Example

Chapter

4 Conjoint Analysis

4.1 Introduction

4.2 How Conjoint Analysis Works

4.3 Managerial Implications

Solved Example 1

Solved Example 2

4.4 Conjoint Analysis in Marketing: New Developments with Implications for

Research and Practice

4.5 Levels of Aggregation In Conjoint Analysis – An Empirical Comparison

Chapter

5 Factor Analysis

5.1 Introduction

5.2 Principal Components Analysis

5.3 Test of Significance

5.4 No. of Principal Components to Be Retained

Solved Example

5.5 Common Factor Analytic Model

5.5.1 Principle Factor Models

Solved Example

5.6 Factor Rotation

5.6.1 Orthogonal Rotation

5.6.1.1 Varimax Rotation

5.6.2 Oblique Rotation

Solved Example

Chapter

6 Canonical Correlation

of 42

6.1 Introduction

6.2 Canonical Loading

6.3 Cross Loading

Solved Example

Chapter

7 Cluster Analysis

7.1 Introduction

7.2 Agglomerative Method

7.2.1 Single Linkage

7.2.2 Complete Linkage

7.2.3 Average Linkage

Solved Example

7.3 Non - Hierarchical Clustering

7.3.1 K-Means Clustering

Solved Example

7.4 Applications of Cluster Analysis

Chapter

8 Multi-Dimensional Scaling (MDS)

8.1 Introduction

8.2 Classification

8.3 Metric and Non-Metric MDS

8.4 Non-Metric MDS Algorithm

8.5 Applications and Limitations

Solved Example

Chapter

9 Multi variate Analysis of Variance (MANOVA)

9.1 Introduction

9.2 One-way ANOVA

9.3 Two-way ANOVA

of 42

Solved Example

9.4 One-way MANOVA

9.5 Two-way MANOVA

9.6 Three-way MANOVA

Solved Example

Declaration

Ihereby declare that all the statements/particulars made/furnished in this application are true,

complete and correct to the best of my knowledge and belief.

National Institute of Technology, Tiruchirappalli 620015 ... 2 of 42 • Head of the Department,...

Documents

Transcript of National Institute of Technology, Tiruchirappalli 620015 ... 2 of 42 • Head of the Department,...